RAG AI Deployments
summary
NetApp and F5 claim a working stack to deploy RAG at scale that marries proprietary data to large models by networking and securing data where it lives. They build a distributed cloud mesh plus deployable customer Edge (CE) software to route and unify silos, place Big‑IP in front of storage (including S3 workflows) to load‑balance and protect hot read traffic, and report customers handling thousands of requests per second into AI factories; the setup reduces policy overhead, eases cloud migrations, and is already running in production for large customers.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 1:26What is RAG
- 7:24Data gravity challenge
- 13:47AI workloads hybrid cloud
- 18:01F5 distributed cloud AI
- 26:28Balancing AI storage
- 31:22Future of AI proprietary data
- 32:44Q&A
related talks
10mApproach to AI at a large scale
19mBuilding Production-Ready RAG Systems
47mRAG at scale: production-ready GenAI apps with Azure AI Search
33mRAG Pipelines Letting You Down? Fitch Group's Solution for Financial Documents
05mAI discussions and deployments in the UK
09mAI, DPUs, and Distributed Workloads: What F5 and Nutanix Are Building Together
16mEmpower your organization with production-ready RAG apps on Azure
42mBuilding Scalable RAG Pipelines with Java and Kubernetes